© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115810
    Prev
    Next
    INDEX
    Explanations

    Native American culture and identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tribal
    -0.81
    zeiger
    -0.81
    LOYEES
    -0.78
    oolean
    -0.76
    gga
    -0.75
     Attorneys
    -0.74
    Tribal
    -0.74
     Newsroom
    -0.74
     tribes
    -0.73
    afone
    -0.73
    POSITIVE LOGITS
     Medicine
    0.97
     Eagle
    0.93
     medicine
    0.93
     Woman
    0.90
     Lodge
    0.88
     lodge
    0.88
    lodge
    0.84
     woman
    0.83
    leggings
    0.80
    bundle
    0.77
    Activations Density 0.022%

    No Known Activations